corpusAccess a user's Corpus library from OpenClaw. Use when the user asks to search saved content, fetch item details, save links into Corpus, or create reminders...
Install via ClawdBot CLI:
clawdbot install doninocode/corpusUse this skill to read and write a user's Corpus data through the Corpus API.
CORPUS_API_TOKEN: user token for Corpus API access.CORPUS_API_TOKENhttps://apps.apple.com/us/app/corpus-ai/id6748364607Integrations -> OpenClaw.CORPUS_API_TOKEN in your OpenClaw skill env.CORPUS_API_BASE_URL: API base URL (default: https://corpusai.app).CORPUS_TIMEOUT_SECONDS: HTTP timeout in seconds (default: 30).{
"skills": {
"entries": {
"corpus": {
"path": "/absolute/path/to/skills/corpus",
"env": {
"CORPUS_API_TOKEN": "csk_live_or_jwt_token_here",
"CORPUS_API_BASE_URL": "https://corpusai.app"
}
}
}
}
}
Run all commands through:
python3 {baseDir}/scripts/corpus_api.py
Available commands:
profilelist-content --limit 20 --cursor search --query "" --limit 8 content --user-content-id save-url --url [--user-note ""] create-reminder --title "" --description "" --scheduled-date-utc "2026-02-18T16:00:00Z" [--user-content-id ] When a user asks for "find items in Corpus and implement":
search with a focused query.content for top hits to collect concrete steps.CORPUS_API_TOKEN.save-url, create-reminder), confirm user intent if the instruction is ambiguous.Generated Mar 1, 2026
A researcher uses the skill to search their saved articles and documents in Corpus, quickly retrieving relevant sources for a literature review. They can also save new URLs with notes directly from their workflow, streamlining the curation process.
A project manager accesses saved links and notes in Corpus to gather requirements or reference materials for a project. They create reminders from this content to schedule follow-ups or deadlines, integrating saved knowledge into task management.
An individual uses the skill to search their personal library of saved web content, such as recipes or travel guides, for quick reference. They can add new items and set reminders based on saved information, enhancing daily organization.
A support agent searches Corpus for internal documentation or past solutions to address customer inquiries efficiently. They save new troubleshooting links with notes for future reference, improving response accuracy and speed.
A writer or journalist searches their Corpus for inspiration or facts from previously saved articles and sources. They save new research URLs and create reminders to follow up on leads, aiding in content development and deadline management.
Offer a premium service where users pay a monthly fee for enhanced Corpus features, such as advanced search analytics, team collaboration tools, and priority API access. Revenue is generated through tiered subscriptions targeting professionals and organizations.
Provide customized integrations of the Corpus skill into corporate workflows, such as CRM or project management systems, with dedicated support and security features. Revenue comes from one-time setup fees and annual licensing contracts for businesses.
Offer a free basic version of the Corpus skill with limited API calls, while charging for higher usage limits, additional storage, or premium commands like automated reminders. Revenue is generated from power users and developers through pay-as-you-go or tiered plans.
💬 Integration Tip
Ensure the CORPUS_API_TOKEN is securely stored and never exposed in logs; use environment variables in deployment to maintain security and ease configuration.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection